{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:KYM24DLWKDJ57YCKL46G6XFEDI","short_pith_number":"pith:KYM24DLW","canonical_record":{"source":{"id":"2501.11468","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2025-01-20T12:56:02Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"99513491ffdeacee6aa302ed5fa191f54b89983b53ef192ac7ff646a1f1f0132","abstract_canon_sha256":"f54389012e63cddc0a260e653fa23c76e0433c663e48f0800586eb7657907b42"},"schema_version":"1.0"},"canonical_sha256":"5619ae0d7650d3dfe04a5f3c6f5ca41a0b86fc69d71d673946bc491b5009505d","source":{"kind":"arxiv","id":"2501.11468","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.11468","created_at":"2026-07-05T10:03:08Z"},{"alias_kind":"arxiv_version","alias_value":"2501.11468v1","created_at":"2026-07-05T10:03:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.11468","created_at":"2026-07-05T10:03:08Z"},{"alias_kind":"pith_short_12","alias_value":"KYM24DLWKDJ5","created_at":"2026-07-05T10:03:08Z"},{"alias_kind":"pith_short_16","alias_value":"KYM24DLWKDJ57YCK","created_at":"2026-07-05T10:03:08Z"},{"alias_kind":"pith_short_8","alias_value":"KYM24DLW","created_at":"2026-07-05T10:03:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:KYM24DLWKDJ57YCKL46G6XFEDI","target":"record","payload":{"canonical_record":{"source":{"id":"2501.11468","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2025-01-20T12:56:02Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"99513491ffdeacee6aa302ed5fa191f54b89983b53ef192ac7ff646a1f1f0132","abstract_canon_sha256":"f54389012e63cddc0a260e653fa23c76e0433c663e48f0800586eb7657907b42"},"schema_version":"1.0"},"canonical_sha256":"5619ae0d7650d3dfe04a5f3c6f5ca41a0b86fc69d71d673946bc491b5009505d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:03:08.976191Z","signature_b64":"BLNitBjgqvBjPbOYqwWCN9OREzCQFZx5TQJcYjt9tdztlNJbIMMPBJcXBFchoHWE4SNumGlfnkoOqNIjFiPrAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5619ae0d7650d3dfe04a5f3c6f5ca41a0b86fc69d71d673946bc491b5009505d","last_reissued_at":"2026-07-05T10:03:08.975707Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:03:08.975707Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2501.11468","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:03:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xvJfF7yNIYet8wS/sVFEYT45Kgx5BzerJ8R5o9qNdaDfp7vRIQqLFSUF0RFY7M4+KTra9+CRZj5YNd0oGsaRBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T23:14:15.678874Z"},"content_sha256":"c39850a77b9426d2d74f7716226fe29c7c3370c4b1a0e6eda2f0b1b669948337","schema_version":"1.0","event_id":"sha256:c39850a77b9426d2d74f7716226fe29c7c3370c4b1a0e6eda2f0b1b669948337"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:KYM24DLWKDJ57YCKL46G6XFEDI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"LLM supervised Pre-training for Multimodal Emotion Recognition in Conversations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Soumya Dutta, Sriram Ganapathy","submitted_at":"2025-01-20T12:56:02Z","abstract_excerpt":"Emotion recognition in conversations (ERC) is challenging due to the multimodal nature of the emotion expression. In this paper, we propose to pretrain a text-based recognition model from unsupervised speech transcripts with LLM guidance. These transcriptions are obtained from a raw speech dataset with a pre-trained ASR system. A text LLM model is queried to provide pseudo-labels for these transcripts, and these pseudo-labeled transcripts are subsequently used for learning an utterance level text-based emotion recognition model. We use the utterance level text embeddings for emotion recognitio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.11468","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2501.11468/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:03:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ec5zb2hQHx3CgifwuHEMwVbtpbtzNAN3xXQdvcYnRhY4s3YWQiiSiioNPNO4wTXcHXGTE7WqzcwPW6S0V1AMDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T23:14:15.679410Z"},"content_sha256":"e961b456233d734df69e7c91a067baf8d26ff0f08a50f66dcadfdec6fe5689e4","schema_version":"1.0","event_id":"sha256:e961b456233d734df69e7c91a067baf8d26ff0f08a50f66dcadfdec6fe5689e4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KYM24DLWKDJ57YCKL46G6XFEDI/bundle.json","state_url":"https://pith.science/pith/KYM24DLWKDJ57YCKL46G6XFEDI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KYM24DLWKDJ57YCKL46G6XFEDI/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-09T23:14:15Z","links":{"resolver":"https://pith.science/pith/KYM24DLWKDJ57YCKL46G6XFEDI","bundle":"https://pith.science/pith/KYM24DLWKDJ57YCKL46G6XFEDI/bundle.json","state":"https://pith.science/pith/KYM24DLWKDJ57YCKL46G6XFEDI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KYM24DLWKDJ57YCKL46G6XFEDI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:KYM24DLWKDJ57YCKL46G6XFEDI","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"f54389012e63cddc0a260e653fa23c76e0433c663e48f0800586eb7657907b42","cross_cats_sorted":["cs.SD"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2025-01-20T12:56:02Z","title_canon_sha256":"99513491ffdeacee6aa302ed5fa191f54b89983b53ef192ac7ff646a1f1f0132"},"schema_version":"1.0","source":{"id":"2501.11468","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.11468","created_at":"2026-07-05T10:03:08Z"},{"alias_kind":"arxiv_version","alias_value":"2501.11468v1","created_at":"2026-07-05T10:03:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.11468","created_at":"2026-07-05T10:03:08Z"},{"alias_kind":"pith_short_12","alias_value":"KYM24DLWKDJ5","created_at":"2026-07-05T10:03:08Z"},{"alias_kind":"pith_short_16","alias_value":"KYM24DLWKDJ57YCK","created_at":"2026-07-05T10:03:08Z"},{"alias_kind":"pith_short_8","alias_value":"KYM24DLW","created_at":"2026-07-05T10:03:08Z"}],"graph_snapshots":[{"event_id":"sha256:e961b456233d734df69e7c91a067baf8d26ff0f08a50f66dcadfdec6fe5689e4","target":"graph","created_at":"2026-07-05T10:03:08Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2501.11468/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Emotion recognition in conversations (ERC) is challenging due to the multimodal nature of the emotion expression. In this paper, we propose to pretrain a text-based recognition model from unsupervised speech transcripts with LLM guidance. These transcriptions are obtained from a raw speech dataset with a pre-trained ASR system. A text LLM model is queried to provide pseudo-labels for these transcripts, and these pseudo-labeled transcripts are subsequently used for learning an utterance level text-based emotion recognition model. We use the utterance level text embeddings for emotion recognitio","authors_text":"Soumya Dutta, Sriram Ganapathy","cross_cats":["cs.SD"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2025-01-20T12:56:02Z","title":"LLM supervised Pre-training for Multimodal Emotion Recognition in Conversations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.11468","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:c39850a77b9426d2d74f7716226fe29c7c3370c4b1a0e6eda2f0b1b669948337","target":"record","created_at":"2026-07-05T10:03:08Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"f54389012e63cddc0a260e653fa23c76e0433c663e48f0800586eb7657907b42","cross_cats_sorted":["cs.SD"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2025-01-20T12:56:02Z","title_canon_sha256":"99513491ffdeacee6aa302ed5fa191f54b89983b53ef192ac7ff646a1f1f0132"},"schema_version":"1.0","source":{"id":"2501.11468","kind":"arxiv","version":1}},"canonical_sha256":"5619ae0d7650d3dfe04a5f3c6f5ca41a0b86fc69d71d673946bc491b5009505d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5619ae0d7650d3dfe04a5f3c6f5ca41a0b86fc69d71d673946bc491b5009505d","first_computed_at":"2026-07-05T10:03:08.975707Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:03:08.975707Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"BLNitBjgqvBjPbOYqwWCN9OREzCQFZx5TQJcYjt9tdztlNJbIMMPBJcXBFchoHWE4SNumGlfnkoOqNIjFiPrAw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:03:08.976191Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.11468","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c39850a77b9426d2d74f7716226fe29c7c3370c4b1a0e6eda2f0b1b669948337","sha256:e961b456233d734df69e7c91a067baf8d26ff0f08a50f66dcadfdec6fe5689e4"],"state_sha256":"90c3aac9beca082ca64480a7a8dc03f6a7bbd934a1208e3442a90cd046230de6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"d3YcLJ/XT/c6dAe7MtH7Md53/AhgX3pSX3BGKNftoKnNfMe5lhDzQUVJ9XLZLtcBti6tmdGkAFhuYqVYSPpwDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T23:14:15.683985Z","bundle_sha256":"a13cd1e805f6dace4e72c27d54fbe7164799161fca1cfdb605598ea40e6b290d"}}